LessWrong (Curated & Popular) "Open sourcing a browser extension that tells you when people are wrong on the internet" by lc
6 snips
Feb 26, 2026 A developer walkthrough of a browser extension that flags sourceable factual errors in articles using your OpenAI key. Reasons for automating manual fact checks are explored, including saved time and reduced duplicated work. Surprising prevalence of errors in recent posts gets highlighted. Possible future features like leaderboards, appeals, and improved site support are discussed.
AI Snips
Chapters
Transcript
Episode notes
OpenErrata Automates Sourcing And Caching Of Corrections
- OpenErrata underlines factual claims in articles using your OpenAI API key and caches results so future readers get instant corrections.
- LC notes this avoids duplicated effort from manual ChatGPT checks and often finds errors within ~5 minutes for mid-length posts.
Share Verification Work To Avoid Duplication
- Encourage community adoption so cached investigations reduce duplicated work and speed up verification for common reads.
- LC argues shared results let people avoid individually pasting articles into ChatGPT, saving time and effort.
Author Surprised At Frequency Of Factual Errors
- LC was surprised by how many recent LessWrong and Substack articles contained at least one or two factual errors even with a conservative prompt.
- He reran investigations after deleting DB rows and the tool often found different valid nits it missed earlier.
